run-0111
capability
citable URL: https://halobench.com/records/run-0111/ — this address never moves; the anchor /records/#run-0111 keeps resolving
date 2026-08-11 · window 2026-08-11T20:08:30Z → 2026-08-11T20:37:05Z
suite tau2-bench-airline@668d3bc · config cfg-0025
depth 32,768 tokens · scoring deterministic
Metrics
| metric | value |
|---|---|
| tasks_passed | 1 |
| tasks_total | 8 |
| mean_score | 0.125 |
turns: total 247 · median 23 · p90 73 · max 73 — machine-written trailer, parsed at build time
Guard chain
not a performance run — no guard required
Per-task trace — the full record, no truncation
| task | reward | turns | seconds |
|---|---|---|---|
| 9 | 0 | 23 | 172 |
| 9 | 0 | 73 | 272 |
| 9 | 0 | 20 | 114 |
| 9 | 0 | 23 | 169 |
| 9 | 0 | 20 | 120 |
| 9 | 1 | 46 | 535 |
| 9 | 0 | 20 | 114 |
| 9 | 0 | 22 | 162 |
reward null = infrastructure error, excluded from every paired computation
Cited by — computed at build time, never stored
claims clm-0049